Teo Reu retweetledi
🚨We present MacroGuide: the first model to generate arbitrary macrocycles in 3D 🎉
How? Topological guidance with persistent homology!🧵⬇️ [1/6]
With @duplessis_alex @mmbronstein @AlexanderTong7 @fjduarteg @ismaililkanc
English
Teo Reu
18 posts
Teo Reu
@TeoReu
2nd-year DPhil at Oxford University. Generative Modeling.
Oxford Katılım Ekim 2021
46 Takip Edilen247 Takipçiler
Neurips spotlight! If you care about failure cases of Rectified Flows and about what gradient variance reveals about the optimality of transport vector fields, check out arxiv.org/abs/2510.18118
English
Teo Reu retweetledi
Flow Matching models often struggle to balance memorization and generalization. 😱
We set out to fix this — by using the geometry of the data manifold.
Introducing Carré du Champ Flow Matching (CDCFM)🧑🎨🥖 — improving generalization without sacrificing sample quality.
English
Teo Reu retweetledi
[1/9]🚀Excited to share our new work, RNE! A plug-and-play framework for everything about diffusion model density and control: density estimation, inference-time control & scaling, energy regularisation. More details👇
Joint work with @jmhernandez233 @YuanqiD, Francisco Vargas
English
Teo Reu retweetledi
We are looking for three AI Research Engineers and Scientists to join us in our London office at @SilurianAI to build physics foundation models for weather and energy. Apply below and feel free to reach out if you have any questions:
ycombinator.com/companies/silu…
English
Teo Reu retweetledi
Knowledge Graph Foundation Models (KGFMs) are at the frontier of graph learning - but we didn’t have a principled understanding of what we can (or can’t) do with them. Now we do! 💡🚀
🧵
with Pablo Barcelo, @ismaililkanc, @mmbronstein, @michael_galkin, @JuanLReutter, @OrthMiguel
English
Teo Reu retweetledi
We're presenting MFM right now! Come check it out in East Ballroom poster # 2411 🩷🩷🩷 @TeoReu @bose_joey @AlexanderTong7 @mmbronstein @Francesco_dgv
Kacper Kapuśniak@KKapusniak1
At #NeurIPS and interested in Flow Matching? Come and find us on Thursday presenting MFM - a generalization of FM with probability paths supported on the data manifold 🗺️ Poster: #2411 East Exhibit Hall A-C ⏲️Thu 12 Dec 11 am-2pm neurips.cc/virtual/2024/p… Reach out to chat!
English
@LogConference @bose_joey @helibenhamu @AlexanderTong7 Graph lovers unite! 🤓✨ Can’t wait to see the generative wizards @bose_joey, @helibenhamu, and @AlexanderTong7 break down Geometric Generative Models like it’s magic. #LoG2024
English
Super exciting tutorials in store for LoG 2024, including this one by generative superstars @bose_joey @helibenhamu @AlexanderTong7 ✨
Sign up for LoG 2024 to get the zoom link and all the details in your mailbox soon: forms.gle/p7sG5bHhDz2NM4…
Joey Bose@bose_joey
Attending the Learning on Graphs conference (@LogConference ) this year? Come check our introductory tutorial to building Geometric Generative Models co-delivered with @helibenhamu and @AlexanderTong7. More details: sites.google.com/view/ggm-log-t… We'll start from the very basics of differential geometry and quickly jump to coding simple diffusion and flow-matching models on fun manifolds!
English
Teo Reu retweetledi
Teo Reu retweetledi
We are happy to announce the Oxford LoG meet-up, LoG-Ox! The event is free to attend and will happen on November 25th.
We plan to have keynote talks, lightning talks, posters and socials. More information and signup form is available here: log-ox.github.io.
@LogConference
English
Teo Reu retweetledi
I am happy to announce that our paper called Metric Flow Match (MFM) has been accepted to @NeurIPSConf #neurips2024 🔥🔥🔥
I am grateful to all my collaborators and see u in Vancouver! ⛰️
@TeoReu @AlexanderTong7 @mmbronstein @bose_joey @Francesco_dgv
Kacper Kapuśniak@KKapusniak1
If data lives on a manifold, how do we design meaningful interpolations between marginals? We present Metric Flow Matching (MFM)… @PPotaptchik @TeoReu @leoeleoleo1 @AlexanderTong7 @mmbronstein @bose_joey @Francesco_dgv 🔗Dive in here: arxiv.org/abs/2405.14780 🧵 (1/12)
English
🦕Proving Approximation Results with minimal assumptions in VP-SDE Diffusion. Explore how SDE choices impact sample quality and gain insights into Score Matching in Denoising Diffusion Models! 🦕
Link: arxiv.org/pdf/2305.09605…
Presented at UAI2024!
GIF
English
Teo Reu retweetledi
If data lives on a manifold, how do we design meaningful interpolations between marginals? We present Metric Flow Matching (MFM)…
@PPotaptchik @TeoReu @leoeleoleo1 @AlexanderTong7 @mmbronstein @bose_joey @Francesco_dgv
🔗Dive in here: arxiv.org/abs/2405.14780
🧵 (1/12)
GIF
English
Teo Reu retweetledi
Strongly recommended: Emily’s first paper during her PhD. Emily is not on X but she will be in Vienna for #ICML2024!
Michael Bronstein@mmbronstein
It’s All About That Homomorphism Basis in our recently accepted #ICML2024 paper: arxiv.org/abs/2402.08595… w/ Emily Jin, @ismaililkanc, and @mat_lanzinger (1/3)
English
Teo Reu retweetledi
A cozy Oxford LoG meetup with guests from London and the Other Place
English
Teo Reu retweetledi
I am excited to announce that our latest work "A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs", together with Miguel Romero, @ismaililkanc, and Pablo Barceló, will be presented in #NeurIPS 2023.
Arxiv link: arxiv.org/pdf/2302.02209…
(1/2)🧵
English